Text-Based Identification of Monetary Policy Shocks
(2026) In Working Papers- Abstract
- This paper identifies monetary policy shocks for Sweden. Based on the written language in
documents prepared by staff ahead of Riksbank policy meetings, I construct text-based regressors that are shown to systematically predict shocks identified with standard methods such as
the Romer and Romer (2004) Greenbook approach and high-frequency identification. Defin-
ing text-based monetary policy shocks as the part of the standard shock that is uncorrelated
with this rich nonstandard source of information, I study the effect of monetary policy on key
monetary aggregates using local projections. The dynamic responses to my text-based policy
shocks are in line with theoretical expectations for a majority of variables at... (More) - This paper identifies monetary policy shocks for Sweden. Based on the written language in
documents prepared by staff ahead of Riksbank policy meetings, I construct text-based regressors that are shown to systematically predict shocks identified with standard methods such as
the Romer and Romer (2004) Greenbook approach and high-frequency identification. Defin-
ing text-based monetary policy shocks as the part of the standard shock that is uncorrelated
with this rich nonstandard source of information, I study the effect of monetary policy on key
monetary aggregates using local projections. The dynamic responses to my text-based policy
shocks are in line with theoretical expectations for a majority of variables at both quarterly
and annual frequency. Text-based Romer and Romer shocks are more in line with ’textbook’
responses compared to high-frequency based shocks. All results are robust to alternative text-
analytic implementations, model specifications and lag length selection in local projections. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/7dd0ee9f-c483-4f1d-9aa7-1128c202222b
- author
- Almgren, Pelle LU
- organization
- publishing date
- 2026-09
- type
- Working paper/Preprint
- publication status
- published
- subject
- keywords
- Monetary Policy Shocks, Textual Analysis, Riksbank, BERT, Local Projections, C22, C38, C45, E32, E52, E58
- in
- Working Papers
- issue
- 2026:10
- pages
- 90 pages
- language
- English
- LU publication?
- yes
- id
- 7dd0ee9f-c483-4f1d-9aa7-1128c202222b
- date added to LUP
- 2026-09-09 13:06:11
- date last changed
- 2026-09-09 13:06:11
@misc{7dd0ee9f-c483-4f1d-9aa7-1128c202222b,
abstract = {{This paper identifies monetary policy shocks for Sweden. Based on the written language in<br/>documents prepared by staff ahead of Riksbank policy meetings, I construct text-based regressors that are shown to systematically predict shocks identified with standard methods such as<br/>the Romer and Romer (2004) Greenbook approach and high-frequency identification. Defin-<br/>ing text-based monetary policy shocks as the part of the standard shock that is uncorrelated<br/>with this rich nonstandard source of information, I study the effect of monetary policy on key<br/>monetary aggregates using local projections. The dynamic responses to my text-based policy<br/>shocks are in line with theoretical expectations for a majority of variables at both quarterly<br/>and annual frequency. Text-based Romer and Romer shocks are more in line with ’textbook’<br/>responses compared to high-frequency based shocks. All results are robust to alternative text-<br/>analytic implementations, model specifications and lag length selection in local projections.}},
author = {{Almgren, Pelle}},
keywords = {{Monetary Policy Shocks; Textual Analysis; Riksbank; BERT; Local Projections; C22; C38; C45; E32; E52; E58}},
language = {{eng}},
note = {{Working Paper}},
number = {{2026:10}},
series = {{Working Papers}},
title = {{Text-Based Identification of Monetary Policy Shocks}},
url = {{https://lup.lub.lu.se/search/files/260382744/WP26_10_cover_combined.pdf}},
year = {{2026}},
}